Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仮
    -0.07
     bài
    -0.06
    -sk
    -0.06
    oca
    -0.06
    売
    -0.06
     Room
    -0.06
     preferring
    -0.06
    čet
    -0.06
     cryptoc
    -0.06
     Alternatively
    -0.06
    POSITIVE LOGITS
    _deep
    0.07
    getSingleton
    0.07
    мест
    0.06
    ustering
    0.06
    วรรณ
    0.06
    rients
    0.06
     bolster
    0.06
    fulness
    0.06
    puties
    0.06
    icol
    0.06
    Act Density 0.000%

    No Known Activations